© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10965
    Prev
    Next
    INDEX
    Explanations

    words describing someone or something, often negatively

    oai_token-act-pair · gemini-2.0-flash

    product descriptions/reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.61
    الدراسه
    -0.57
    ertale
    -0.55
     continúas
    -0.52
    [--
    -0.48
    +#+#
    -0.48
    tvguidetime
    -0.47
     Nadel
    -0.46
    domen
    -0.45
    smarty
    -0.45
    POSITIVE LOGITS
     ExecuteAsync
    0.61
    Lax
    0.55
    πάρχ
    0.53
     Lax
    0.52
    Beg
    0.52
    లాలు
    0.52
    PYX
    0.51
    <%=
    0.51
    ErrorListener
    0.51
     />';
    0.50
    Activations Density 0.482%

    No Known Activations